Learning disentangled feature representation for hybrid-distorted image restoration

Li, Xin, Jin, Xin, Lin, Jianxin, Liu, Sen, Wu, Yaojun, Yu, Tao, Zhou, Wei and Chen, Zhibo 2020. Learning disentangled feature representation for hybrid-distorted image restoration. Presented at: 16th European Conference on Computer Vision (ECCV 2020), Glasgow, Scotland, 23-28 August 2020. Published in: Vedaldi, Andrea, Bischof, Horst, Brox, Thomas and Frahm, Jan-Michael eds. Computer Vision – ECCV 2020 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XXIX. Lecture Notes in Computer Science Springer, pp. 313-329. 10.1007/978-3-030-58526-6_19

Full text not available from this repository.

Abstract

Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions. Existing HD-IR approaches usually ignore the inherent interference among hybrid distortions which compromises the restoration performance. To decompose such interference, we introduce the concept of Disentangled Feature Learning to achieve the feature-level divide-and-conquer of hybrid distortions. Specifically, we propose the feature disentanglement module (FDM) to distribute feature representations of different distortions into different channels by revising gain-control-based normalization. We also propose a feature aggregation module (FAM) with channel-wise attention to adaptively filter out the distortion representations and aggregate useful content information from different channels for the construction of raw image. The effectiveness of the proposed scheme is verified by visualizing the correlation matrix of features and channel responses of different distortions. Extensive experimental results also prove superior performance of our approach compared with the latest HD-IR schemes.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Springer
ISBN:	978-3-030-58525-9
ISSN:	0302-9743
Last Modified:	27 Sep 2023 16:30
URI:	https://orca.cardiff.ac.uk/id/eprint/162067

Actions (repository staff only)

Edit Item